Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ISBNs and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sixty
    0.44
     Edited
    0.42
     Sixth
    0.41
     Policing
    0.41
     দ্বিতীয়
    0.40
    出版社
    0.40
     series
    0.39
     edited
    0.39
     第二
    0.38
    खोरी
    0.38
    POSITIVE LOGITS
    ดิ
    0.38
    اہم
    0.38
    蒖
    0.38
    说法
    0.38
    تا
    0.37
    Rational
    0.37
    Hozzáférés
    0.37
    Poke
    0.36
    ቕ
    0.36
     കാ
    0.36
    Act Density 0.000%

    No Known Activations